Multi-agent online learning in time-varying games - POLARIS - Performance analysis and Optimization of LARge Infrastructure and Systems Access content directly
Journal Articles Mathematics of Operations Research Year : 2023

Multi-agent online learning in time-varying games

Abstract

We examine the long-run behavior of multi-agent online learning in games that evolve over time. Specifically, we focus on a wide class of policies based on mirror descent, and we show that the induced sequence of play (a) converges to Nash equilibrium in time-varying games that stabilize in the long run to a strictly monotone limit; and (b) it stays asymptotically close to the evolving equilibrium of the sequence of stage games (assuming they are strongly monotone). Our results apply to both gradient-based and payoff-based feedback - i.e., when players only get to observe the payoffs of their chosen actions.
Fichier principal
Vignette du fichier
Main.pdf (737.42 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01891545 , version 1 (21-12-2023)

Licence

Attribution

Identifiers

Cite

Benoît Duvocelle, Panayotis Mertikopoulos, Mathias Staudigl, Dries Vermeulen. Multi-agent online learning in time-varying games. Mathematics of Operations Research, 2023, 48 (2), pp.914-941. ⟨10.1287/moor.2022.1283⟩. ⟨hal-01891545⟩
153 View
6 Download

Altmetric

Share

Gmail Facebook X LinkedIn More